11,195 prices on 4,854 listings · last collected 5 h ago · 442 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on ten platforms, daily by default, and keeps the page it read. Nothing is typed in by hand. Search a model to see who charges least, per unit, right now.
Platform
Unit price
All 11,195Per second of output 2,701Per minute 34Per video 674Per image 1,827Per megapixel 326Per million input tokens 1,298Per million output tokens 1,235Per million tokens 47Per million cached input tokens (read) 641Per million cache-write tokens 227Per thousand characters 75Per second of compute time 98Per run (default parameters) 1,784Other units (see the platform’s wording) 228
Showing 5601–5700 of 11,195
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterThird-party | OpenAI: gpt-oss-120b (batch) | $0.03/M in | prompt: 0.0000000296 / token (endpoint deepinfra/bf16) | |
| AibermNot disclosed | Text Embedding 3 Large | $0.03/M in | model_ratio 0.065 × $2/M · group default ×0.23Claims official price $0.13/M in | |
| KIENot disclosed | gpt-6-luna | $0.03/M in | 6 credits per million tokens ($0.03)Claims official or Fal price $0.1/M in | |
| OpenRouterOfficial | Inference.net: Schematron V2 Turbovia InferenceNet · bf16 | $0.03/M in | prompt: 0.00000003 / token (endpoint inference-net/bf16) | |
| OpenRouterOfficial | Qwen: Qwen3.7 Flashvia Alibaba | $0.03/M in | prompt: 0.00000003 / token (endpoint alibaba) | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.0-2b-instruct | $0.03/M in | $0.03 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.1-2b-instruct | $0.03/M in | $0.03 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.1-8b-instruct | $0.03/M in | $0.03 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.2-8b-instruct | $0.03/M in | $0.03 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.3-8b-instruct | $0.03/M in | $0.03 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-speech-4.1-2b | $0.03/M in | $0.03 per million input tokens | |
| OpenRouterOfficial | Amazon: Nova Micro 1.0via Amazon Bedrock | $0.035/M in | prompt: 0.000000035 / token (endpoint amazon-bedrock) | |
| OpenRouterThird-party | OpenAI: gpt-oss-120bvia PrimeIntellect · fp4 | $0.035/M in | prompt: 0.000000035 / token (endpoint primeintellect/fp4) | |
| OpenRouterOfficial | Cohere: Command R7B (12-2024) | $0.038/M in | prompt: 0.0000000375 / token (endpoint cohere) | |
| OpenRouterNot disclosed | Z.ai: GLM 5.3 Flashvia Relace · fp4 | $0.04/M in | prompt: 0.0000000399 / token (endpoint relace/fp4) | |
| OpenRouterNot disclosed | Z.ai: GLM Flash Latest | $0.04/M in | prompt: 0.0000000399 / token | |
| APIMartNot disclosed | gpt-5-nano | $0.04/M in | Input $0.04 / Output $0.32 · Per 1M tokens | |
| APIMartNot disclosed | gpt-5-nano-2025-08-07 | $0.04/M in | Input $0.04 / Output $0.32 · Per 1M tokens | |
| OpenRouterThird-party | Google: Gemma 3 4Bvia Parasail · bf16 | $0.04/M in | prompt: 0.00000004 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Sao10K: Llama 3 8B Lunarisvia Parasail · bf16 | $0.04/M in | prompt: 0.00000004 / token (endpoint parasail/bf16) | |
| OpenRouterOfficial | ScaleDown: Extract | $0.04/M in | prompt: 0.00000004 / token (endpoint scaledown) | |
| OpenRouterOfficial | ScaleDown: Summarize | $0.04/M in | prompt: 0.00000004 / token (endpoint scaledown) | |
| RunwareNot disclosed | Jev 1.13 | $0.042/M in | $4.2e-8 / inputToken | |
| RunwareNot disclosed | Jev 1.14 | $0.042/M in | $4.2e-8 / inputToken | |
| OpenRouterNot disclosed | DeepSeek: DeepSeek V4 Flash Latest | $0.043/M in | prompt: 0.0000000434 / token | |
| OpenRouterOfficial | Tencent: Hy-MT2-1.8B | $0.044/M in | prompt: 0.000000044 / token (endpoint tencent/fp8) | |
| OpenRouterThird-party | inclusionAI: Ling 3.1 Flash | $0.045/M in | prompt: 0.000000045 / token (endpoint novita) | |
| APIMartNot disclosed | deepseek-ocr | $0.046/M in | Input $0.0456 / Output $0.2052 · Per 1M tokens | |
| OpenRouterThird-party | Z.ai: GLM 5.3 Flash (batch)via Morph · fp8 | $0.047/M in | prompt: 0.000000047 / token (endpoint morph/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash 0731 (batch) | $0.048/M in | prompt: 0.000000048 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash 0423via Baidu · fp8 | $0.05/M in | prompt: 0.00000004998 / token (endpoint baidu/fp8) | |
| OpenRouterOfficial | Anthropic: Claude Haiku 5.5 (batch) | $0.05/M in | prompt: 0.00000005 / token (endpoint anthropic) | |
| OpenRouterOfficial | Inference.net: Schematron V2 Smallvia InferenceNet · bf16 | $0.05/M in | prompt: 0.00000005 / token (endpoint inference-net/bf16) | |
| OpenRouterOfficial | LiquidAI: LFM2.5-24B-A2B | $0.05/M in | prompt: 0.00000005 / token (endpoint liquid/fp8) | |
| OpenRouterThird-party | Meta: Llama 3.2 3B Instructvia Parasail · bf16 | $0.05/M in | prompt: 0.00000005 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Mistral: Mistral Small 3 | $0.05/M in | prompt: 0.00000005 / token (endpoint deepinfra/fp8) | |
| OpenRouterOfficial | OpenAI: GPT-4.1 Nano (batch) | $0.05/M in | prompt: 0.00000005 / token (endpoint openai) | |
| OpenRouterOfficial partner | OpenAI: GPT-5 Nanovia Azure | $0.05/M in | prompt: 0.00000005 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna Pro (batch) | $0.05/M in | prompt: 0.00000005 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-6 Luna (batch) | $0.05/M in | prompt: 0.00000005 / token (endpoint openai) | |
| OpenRouterOfficial | Particle AI: Particle-1 | $0.05/M in | prompt: 0.00000005 / token | |
| OpenRouterOfficial | Upstage: Solar Mini 4via Upstage · zdr | $0.05/M in | prompt: 0.00000005 / token (endpoint upstage/zdr) | |
| ReplicatePlatform-hosted | ibm-granite/granite-3.0-8b-instruct | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-8b-code-instruct-128k | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | meta/llama-2-7b | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | meta/llama-2-7b-chat | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-8b | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-8b-instruct | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | mistralai/mistral-7b-v0.1 | $0.05/M in | $0.05 per million input tokens | |
| ReplicateOfficial partner | openai/gpt-5-nano | $0.05/M in | $0.05 per million input tokens | |
| ReplicateOfficial partner | openai/gpt-5-structuredgpt-5-nano | $0.05/M in | $0.05 per million input tokens (gpt-5-nano) | |
| KIENot disclosed | gpt-5.6-luna | $0.056/M in | 11.2 credits per million tokens ($0.056)Claims official or Fal price $0.2/M in | |
| AibermNot disclosed | GPT-4.1 Mini | $0.06/M in | model_ratio 0.13 × $2/M · group default ×0.23Claims official price $0.4/M in | |
| APIMartNot disclosed | glm-5.3-flash | $0.06/M in | Input $0.06 / Output $0.2 · Per 1M tokens | |
| KIENot disclosed | claude-haiku-5-5 | $0.06/M in | 12 credits per million tokens ($0.06)Claims official or Fal price $0.1/M in | |
| OpenRouterOfficial | Amazon: Nova Lite 1.0via Amazon Bedrock | $0.06/M in | prompt: 0.00000006 / token (endpoint amazon-bedrock) | |
| OpenRouterThird-party | IBM: Granite 4.2 8Bvia CoreWeave · bf16 | $0.06/M in | prompt: 0.00000006 / token (endpoint coreweave/bf16) | |
| OpenRouterThird-party | inclusionAI: Ling 3.0 Flash VL | $0.06/M in | prompt: 0.00000006 / token (endpoint deepinfra/fp16) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3 Nano 30B A3B | $0.06/M in | prompt: 0.00000006 / token (endpoint nebius/fp8) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3.5 Super VLvia Darkbloom · nvfp4 | $0.06/M in | prompt: 0.00000006 / token (endpoint darkbloom/nvfp4) | |
| ReplicatePlatform-hosted | ibm-granite/granite-4.0-h-small | $0.06/M in | $0.06 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-4.1-8b | $0.06/M in | $0.06 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-4.2-8b | $0.06/M in | $0.06 per million input tokens | |
| ReplicatePlatform-hosted | ibm-granite/granite-vision-4.1-4b | $0.06/M in | $0.06 per million input tokens | |
| OpenRouterThird-party | Z.ai: GLM 4.7 Flashvia Cloudflare | $0.061/M in | prompt: 0.0000000605 / token (endpoint cloudflare) | |
| OpenRouterThird-party | Qwen: Qwen3.8 27Bvia PrimeIntellect · fp8 | $0.062/M in | prompt: 0.000000062 / token (endpoint primeintellect/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3.5-35B-A3Bvia Darkbloom · fp4 | $0.065/M in | prompt: 0.000000065 / token (endpoint darkbloom/fp4) | |
| OpenRouterOfficial | Qwen: Qwen3.5-Flash | $0.065/M in | prompt: 0.000000065 / token (endpoint alibaba) | |
| AibermNot disclosed | GPT-5 Mini | $0.069/M in | model_ratio 0.15 × $2/M · group default ×0.23Claims official price $0.25/M in | |
| OpenRouterNot disclosed | Z.ai: GLM Latest | $0.07/M in | prompt: 0.0000000699 / token | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash 0731via Relace · fp4 | $0.07/M in | prompt: 0.00000007 / token (endpoint relace/fp4) | |
| OpenRouterThird-party | Microsoft: Phi 4via DeepInfra · bf16 | $0.07/M in | prompt: 0.00000007 / token (endpoint deepinfra/bf16) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder 30B A3B Instructvia SiliconFlow · fp8 | $0.07/M in | prompt: 0.00000007 / token (endpoint siliconflow/fp8) | |
| RunwareNot disclosed | gpt-oss-safeguard-20b | $0.07/M in | $7e-8 / inputToken | |
| AibermNot disclosed | Claude Haiku 5.5 | $0.074/M in | model_ratio 0.16 × $2/M · group default ×0.23Claims official price $0.1/M in | |
| AibermNot disclosed | Gemini 2.5 Flash | $0.074/M in | model_ratio 0.16 × $2/M · group default ×0.23Claims official price $0.3/M in | |
| OpenRouterOfficial | Tencent: Hy-MT2-30B-A3B | $0.074/M in | prompt: 0.000000074 / token (endpoint tencent/fp8) | |
| OpenRouterOfficial | Tencent: Hy-MT2-7B | $0.074/M in | prompt: 0.000000074 / token (endpoint tencent/fp8) | |
| OpenRouterThird-party | Google: Gemma 3 12Bvia NextBit · int4 | $0.075/M in | prompt: 0.000000075 / token (endpoint nextbit/int4) | |
| OpenRouterThird-party | Mistral: Mistral Small 3.2 24Bvia DeepInfra · fp8 | $0.075/M in | prompt: 0.000000075 / token (endpoint deepinfra/fp8) | |
| OpenRouterOfficial | Nex AGI: Nex-N2.5-Pro | $0.075/M in | prompt: 0.000000075 / token (endpoint nex-agi/fp8) | |
| OpenRouterThird-party | NVIDIA: Nemotron 3 Supervia DeepInfra · bf16 | $0.075/M in | prompt: 0.000000075 / token (endpoint deepinfra/bf16) | |
| OpenRouterOfficial | OpenAI: GPT-4o-mini (batch) | $0.075/M in | prompt: 0.000000075 / token (endpoint openai) | |
| OpenRouterThird-party | OpenAI: gpt-oss-safeguard-20b | $0.075/M in | prompt: 0.000000075 / token | |
| OpenRouterThird-party | PrismML: Ternary Bonsai 2 27B | $0.075/M in | prompt: 0.000000075 / token (endpoint darkbloom/int4) | |
| RunwareNot disclosed | DeepSeek-V4-Flash-0731 | $0.076/M in | $7.6e-8 / inputToken | |
| APIMartNot disclosed | claude-haiku-5-5 | $0.08/M in | Input $0.08 / Output $0.4 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4.1-nano | $0.08/M in | Input $0.08 / Output $0.32 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4.1-nano-2025-04-14 | $0.08/M in | Input $0.08 / Output $0.32 · Per 1M tokens | |
| APIMartNot disclosed | gpt-6-luna | $0.08/M in | Input $0.08 / Output $0.4 · Per 1M tokens | |
| APIMartNot disclosed | text-embedding-ada-002 | $0.08/M in | Input $0.08 / Output $0.08 · Per 1M tokens | |
| OpenRouterThird-party | Google: Gemma 3 27Bvia DeepInfra · fp8 | $0.08/M in | prompt: 0.00000008 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | MythoMax 13Bvia Parasail · fp16 | $0.08/M in | prompt: 0.00000008 / token (endpoint parasail/fp16) | |
| OpenRouterOfficial | LiquidAI: LFM3-1.7B | $0.08/M in | prompt: 0.00000008 / token (endpoint liquid/fp8) | |
| OpenRouterThird-party | PrismML: Ternary Bonsai 2 9B | $0.08/M in | prompt: 0.00000008 / token (endpoint darkbloom/int4) | |
| OpenRouterThird-party | Qwen: Qwen3 32Bvia DeepInfra · fp8 | $0.08/M in | prompt: 0.00000008 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3.5-9Bvia Darkbloom · fp4 | $0.08/M in | prompt: 0.00000008 / token (endpoint darkbloom/fp4) | |
| OpenRouterThird-party | Tencent: Hy3off-peak 1600–0000 UTC · via Tencent · fp8 | $0.083/M in | prompt: 0.0000000825 / token (utc_start 1600, utc_end 0; endpoint tencent/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 235B A22B Instruct 2507via DeepInfra · fp8 | $0.09/M in | prompt: 0.00000009 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 30B A3B Instruct 2507via DekaLLM | $0.09/M in | prompt: 0.00000009 / token (endpoint dekallm) |
